Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical quantities or statistics related to data or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iedler
    -0.66
    classmethod
    -0.61
     present
    -0.60
     Nuss
    -0.59
     very
    -0.59
    czaj
    -0.58
    ANGEL
    -0.57
     Sommers
    -0.57
    ı
    -0.57
    dehydes
    -0.57
    POSITIVE LOGITS
    0
    1.17
    awtextra
    0.93
    AndEndTag
    0.87
     defaultstate
    0.78
     Athene
    0.76
    ^(@)
    0.75
     crdi
    0.73
    ０
    0.73
    vician
    0.72
    stattung
    0.70
    Act Density 0.661%

    No Known Activations